paper-with-me

Papers

Which Backbone to Use: A Resource-efficient Domain Specific Comparison for Computer Vision

2024-06-09 · Pranav Jeevan, Amit Sethi

In contemporary computer vision applications, particularly image classification, architectural backbones pre-trained on large datasets like ImageNet are commonly employed as feature extractors. Despite the widespread use of these pre-trained convolutional neural networks (CNNs), there remains a gap in understanding the performance of various resource-efficient backbones across diverse domains and dataset sizes. Our study systematically evaluates multiple lightweight, pre-trained CNN backbones under consistent training settings across a variety of datasets, including natural images, medical images, galaxy images, and remote sensing images. This comprehensive analysis aims to aid machine learning practitioners in selecting the most suitable backbone for their specific problem, especially in scenarios involving small datasets where fine-tuning a pre-trained network is crucial. Even though attention-based architectures are gaining popularity, we observed that they tend to perform poorly under low data finetuning tasks compared to CNNs. We also observed that some CNN architectures such as ConvNeXt, RegNet and EfficientNet performs well compared to others on a diverse set of domains consistently. Our findings provide actionable insights into the performance trade-offs and effectiveness of different backbones, facilitating informed decision-making in model selection for a broad spectrum of computer vision domains. Our code is available here: https://github.com/pranavphoenix/Backbones

📄 PDF Abstract BibTeX arXiv:2406.05612

Code (1)

pranavphoenix/Backbones 공식 구현 pytorch

Tasks

Breast Cancer Histology Image ClassificationDecision Makingimage-classificationImage ClassificationModel Selection

Methods 이 논문이 사용한 방법론

ReLU How Do I Communicate to Expedia? How Do I Communicate to Expedia? – Call ☎️ +1-(888) 829 (0881) or +1-805-330-4056 or +1-805-330-4056 for Live Support & Special Travel…
SET Dynamic Sparse Training method where weight mask is updated randomly periodically
Batch Normalization 설명 없음
Dropout Dropout is a regularization technique for neural networks that drops a unit (along with connections) at training time with a specified probability $p$ (a common value is…
Dense Connections Dense Connections, or Fully Connected Connections, are a type of layer in a deep neural network that use a linear operation where every input is connected to every output…
Squeeze-and-Excitation Block The Squeeze-and-Excitation Block is an architectural unit designed to improve the representational power of a network by enabling it to perform dynamic channel-wise feature…
Pointwise Convolution Pointwise Convolution is a type of convolution that uses a 1x1 kernel: a kernel that iterates through every single point. This…
Convolution A convolution is a type of matrix operation, consisting of a kernel, a small matrix of weights, that slides over input data performing element-wise multiplication with the…

Similar Papers 제목 키워드 기반

Domain Adaptation for Japanese Sentence Embeddings with Contrastive Learning based on Synthetic Sentence Generation

2025-03-12 · Zihao Chen, Hisashi Handa, Miho Ohsaki, Kimiaki Shirahama

Several backbone models pre-trained on general domain datasets can encode a sentence into a widely useful embedding. Such sentence embeddings can be further enhanced by domain adaptation that adapts a backbone model to a…

Contrastive LearningDomain AdaptationSemantic Textual SimilaritySentence+2

Leveraging Domain Adaptation and Data Augmentation to Improve Qur'anic IR in English and Arabic

2023-12-05 · Vera Pavlova

In this work, we approach the problem of Qur'anic information retrieval (IR) in Arabic and English. Using the latest state-of-the-art methods in neural IR, we research what helps to tackle this task more efficiently. Tra…

Data AugmentationDomain AdaptationInformation RetrievalLanguage Modelling+1

Domain-specific Language Pre-training for Dialogue Comprehension on Clinical Inquiry-Answering Conversations

2022-06-06 · Zhengyuan Liu, Pavitra Krishnaswamy, Nancy F. Chen

There is growing interest in the automated extraction of relevant information from clinical dialogues. However, it is difficult to collect and construct large annotated resources for clinical dialogue tasks. Recent devel…

Reading Comprehension

Dynamic Topic Modeling for Cross-Corpus Temporal Analysis

2026-08-24 · Ruoxuan Li, Bruce Kogut arxiv

Dynamic Embedded Topic Models (D-ETM) provide an interpretable framework for modeling temporal semantic evolution, but cross-corpus comparison remains difficult because topics are often learned independently and aligned …

Topic Models

TALI: Protein Structure Alignment Using Backbone Torsion Angles

2020-12-12 · Xijiang Miao, Michael G. Bryson, Homayoun Valafar

This article introduces a novel protein structure alignment method (named TALI) based on the protein backbone torsion angle instead of the more traditional distance matrix. Because the structural alignment of the two pro…